### sparse version checks - [x] I checked that this issue has not been reported before [list of issues](https://github.com/pydata/sparse/issues). - [x] I have confirmed this bug exists on the latest version of sparse. - [x] I have confirmed this bug exists on the main branch of sparse. ### Describe the bug The Array API specification [states](https://data-apis.org/array-api/latest/API_specification/generated/array_api.unique_values.html#unique-values) for `unique_*` functions: > As nan values compare as False, nan values should be considered distinct. In other words, it dictates behaviour equal to `np.unique(..., equal_nan=False)`. `sparse.unique_*` functions however treat NaNs as equal. ### Steps or code to reproduce the bug ```python >>> from math import nan >>> import array_api_strict as xp >>> xp.unique_values(xp.asarray([math.nan, math.nan])) Array([nan, nan], dtype=array_api_strict.float64) >>> import sparse >>> sparse.unique_values(sparse.asarray([math.nan, math.nan])) array([nan]) ``` ### Please describe your system. sparse 0.16.0b4